KR102004199B1 - Processing high dynamic range images - Google Patents

Abstract

Several implementations deal with high dynamic range ("HDR") images. In one particular implementation, a low dynamic range ("LDR") image is generated from the HDR image and information is generated that allows the HDR image to be recovered from the LDR image. The LDR image and its information are encoded. In another implementation, the signal or signal structure comprises an LDR section comprising an encoded LDR image, and an information section containing encoded information. In another implementation, both the encoded LDR image and the encoded information are decoded. The HDR image is then restored based on the decoded LDR image and the decoded information.

Description

[0001] PROCESSING HIGH DYNAMIC RANGE IMAGES [0002]

Implementations related to digital images are described. Several specific implementations relate to high dynamic range ("HDR") images.

Technology allows for more complex images, such as images, which may represent a larger range of colors or brightness, for example. Such images are often referred to as HDR images. In contrast, standard images are often referred to as low dynamic range ("LDR") images. Coding HDR images provides a variety of technical challenges.

According to a general aspect, a lower dynamic range image is generated from a higher dynamic range. Information is generated from the higher dynamic range image and allows for restoration of the higher dynamic range image. The lower dynamic range image and its information are encoded.

According to another general aspect, the signal or signal structure includes a lower dynamic range section including an encoded lower dynamic range image. The signal or signal structure further includes an information section containing encoded information. The information allows restoration of higher dynamic range images from lower dynamic range images.

According to another general aspect, the encoded lower dynamic range image is decoded. The encoded information is also decoded. The information allows restoration of higher dynamic range images from lower dynamic range images. The higher dynamic range image is reconstructed based on the decoded lower dynamic range image and the decoded information.

The details of one or more implementations are set forth in the accompanying drawings and the description below. Although described in one particular manner, it should be clear that implementations may be constructed or embodied in various ways. For example, one implementation may be implemented as a method, or may be implemented as a device, such as an apparatus, or a signal, such as an apparatus that stores instructions to perform a set of operations or a set of operations configured to perform a set of operations. Other aspects and features will become apparent from the following detailed description considered in conjunction with the accompanying drawings and claims.

1 is a flow chart illustrating an implementation of an apparatus and process for processing HDR images.
2 is a flow chart illustrating an implementation of an encoding apparatus and process.
3 is a flow chart illustrating an implementation of a decoding apparatus and process.
4 is a block diagram illustrating an implementation of an encoder and encoding process.
5 is a block diagram illustrating an implementation of a decoder and decoding process.
6 is a block diagram illustrating an implementation of a transmission system and process that may be used in one or more implementations.
7 is a block diagram illustrating an example of a receiving system and process that may be used in one or more implementations.

As a preview of some of the features presented in this application, at least one implementation describes the decomposition of an HDR image into an LDR image and either an exposure map or a lookup table ("LUT"). Along with either the exposure map or the LUT, the LDR image is encoded and inserted into the bitstream for transmission for storage. The LDR image and exposure map may be jointly encoded in some ways. For example, the exposure map may be coded based on restoration of the encoded LDR image. A receiver accesses a bit stream, for example, by receiving a transmission with encoded data, and reads the bit stream from the storage device. The decoder at the receiving end then decodes the LDR image and, if present, the exposure map or LUT. Based on the decoded information, the receiver reconstructs the HDR image. Various implementations are discussed in greater detail below, including exposure map implementations and LUT implementations.

Continuing with the preview, various implementations involving an exposure map can be generally characterized as having the following steps of encoding an HDR video signal:

1. HDR decomposition: decomposes the original HDR image into two layers, the LDR layer and the exposure map layer.

The exposure map is typically defined as a two-dimensional matrix that represents the multiplier (or gain) that each entry may be used to recover the HDR source from the LDR image at the corresponding pixel coordinates. This means that for each pixel coordinate (x, y) the following equation is maintained:

here,

f (.) is an inverse response function that maps a gamma corrected value to a linear value,

C is a constant that results in an LDR image and an exposure map that is in the desired or reasonable range of values,

H is the HDR source value,

L is the LDR image value,

E is the exposure map value.

From the above definition, there may be many ways to decompose an HDR image / video. However, for compression applications, several implementations decompose the HDR source in such a way that the exposure map is a piecewise smoothed signal. It means that the exposure map has strong correlations with the large edges in the original HDR image while smoothing the small-scale details in the HDR im- age.

Note that various implementations determine the exposure map based on the reconstructed values of the HDR source value and the LDR image value. That is, the LDR image value is encoded and decoded to produce a reconstructed LDR image value. This reconstructed LDR image value is then used to determine the exposure map value along with the original HDR source value. In some of these implementations, the exposure map is encoded without loss, possibly allowing for a complete reconstruction of the HDR source value.

2. For example, H.264 (ie, International Organization for Standardization / International Electrotechnical Commission ("ISO / IEC") Moving Picture Experts Group -4 ("MPEG-4") Part 10 Advanced Video Coding "AVC") standards / international telecommunication union, telecommunication sector ("ITU-T") H.264 Recommendation (hereinafter referred to as "H.264 / MPEG-4 AVC standard"Quot;, or simply "AVC" or "H.264 ", their variants).

3. Use the restored LDR layer to help compress the exposure map layer.

In addition, several implementations involving an exposure map can be generally characterized as having the following steps at the decoder side:

1. Extract the bitstream belonging to the LDR layer and decode the LDR layer using the conventional decoder.

2. Use reconstructed LDR frames to aid decoding of the exposure map layer.

3. Combine the reconstructed LDR layer, and the decoded exposure map layer, to reconstruct the HDR video signal.

Referring to FIG. 1, a flow diagram is shown that illustrates components of system 100 that apply to several different implementations. Figure 1 will be used to discuss various implementations.

The system 100 includes five sections. These are the decomposition section 102, the encoding section 104, the signal section 105, the decode section 107, and the reconstruction section 109.

The decomposition section 102 may also be referred to as a decomposition section. The decomposition section 102 receives the HDR image 110 and decomposes the HDR image 110 into an LDR image 112 and reconstruction information 114.

An HDR image is often defined as an image with more than 8 bits per pixel. Conversely, an LDR image is often defined as an image with less than 8 bits per pixel. However, the terms HDR and LDR are relative terms and may refer to images having any number of bits per pixel. Accordingly, at the time of this application, the terms "higher" dynamic range and "lower" dynamic range are used to refer to these images.

Arrow 113 links LDR image 112 and reconstruction information 114. The arrows 113 indicate whether the LDR image 112 is based on the reconstruction information 114 or the reconstruction information 114 is based on the LDR image 112 or both in various implementations, .

Reconfiguration information 114 is, for example, exposure map 116 or LUT 118 in the different implementations discussed herein. The LUT 118 is for example a forward LUT or a backward LUT (abbreviated as "F or B LUT" in FIG. 1). The forward LUT as further described below provides a LUT that is used to determine the LDR image 112 from the HDR image 110. The reverse LUT as described further below provides a LUT that may be used to generate a reconstruction of the HDR image 110 from the reconstruction of the LDR image 112. The reverse LUT is often an inverse of the forward LUT or is based on the forward LUT in some schemes.

The reconstruction information 114 may be used to reconstruct the HDR image 110 from the LDR image 112 more generally. The reconstruction information may include information describing the decomposition of the HDR image 110, information (e.g., a forward LUT), or an inverse of the decomposition of the HDR image 110, in different implementations , Reverse LUT). The reconfiguration information may be referred to in various contexts, and also as decomposition information or component information.

The reconstruction information may also be referred to as reconstruction information. Restoration is a more general term than reconstruction, and reconstructing an HDR image can also be referred to as restoring an HDR image. Restoring an image generally refers to any process that creates an image from component or component information. The component or component information includes, for example, an LDR image, a LUT, an exposure map, a coding reference, or a residue in different implementations. The restored image may, in various implementations, be an estimate of the original image or the same as the original image. As should be apparent, the reconstructed image is a reconstructed image.

However, in this document, the term "reconstruction" is generally used to refer to generating an HDR image by combining several component parts (e.g., an LDR image and an exposure map or LUT). Also, in this document, the term "reconstruction " is generally used to refer to the process of generating an image by decoding several syntax elements to generate an image and using these decoded syntax elements. A typical reconstruction process may include (i) DCT coefficients that represent a residue from, for example, encoding a picture, and information that identifies a reference (e.g., motion vectors and coding mode indicators) Decoding the syntax elements, and (ii) generating an estimate of the picture based on the decoded residue and the identified reference. However, from time to time, the term "reconstruction" includes "reconstruction " and is used in this document as a more general term wider than" reconstruction ".

The encode section 104 receives the LDR image 112. The encoding section 104 encodes the LDR image 112 to generate an encoded LDR image 122. Encoding section 104 also receives exposure map 116 in various implementations. Encoding section 104 encodes exposure map 116 to generate an encoded exposure map 126. Encode section 104 also receives LUT 118 in various implementations. Encode section 104 encodes LUT 118 to generate an encoded LUT 128 that is a forward LUT or a backward LUT as previously described.

The signal section 105 receives the encoded LDR image 122. The signal section 105 forms a signal, for example a bit stream suitable for transmission or storage. The signal section 105 forms an LDR signal portion 132 (abbreviated as "LDR portion" in FIG. 1) of the signal based on the encoded LDR image 122. The signal section 105 also receives the encoded exposure map 126 or the encoded LUT 128 in various implementations described in this application. The signal section 105 forms the reconstruction information signal portion 134 based on either the encoded exposure map 126 or the encoded LUT 128, or possibly both.

The decode section 107 receives the LDR signal section 132. The decode section 107 decodes the LDR signal portion 132 to form a decoded LDR image also referred to as the recovered LDR image 142. [ The decode section 107 also receives the reconfiguration information signal section 134. The decode section 107 decodes the reconfiguration information signal section 134. Depending on what information is included in the reconstruction information signal portion 134, the decode section 107 may be configured to (i) restore the reconstructed exposure map 146, (ii) the reconstructed forward LUT 148, or (iii) And generates one or possibly more of the reverse LUT 149. [

Reconstruction section 109 may also be referred to as a reconstruction section or restoration section. The reconstruction section 109 receives the reconstructed LDR image 142. Reconstruction section 109 may also include one or more of (i) reconstructed exposure map 146, (ii) reconstructed forward LUT 148, or (iii) reconstructed reverse LUT 149, And receives more than that.

In order to use the reconstructed LDR image 142 and reconstruct the HDR image using the LUT, the reconstruction section 109 of the system 100 uses a reverse LUT. That is, by definition, the backward LUT receives the LDR data value as an input and provides the HDR data value as an output. Thus, when a reconstructed forward LUT 148 is received, the reconstruction section 109 generates a backward LUT 158 generated based on the reconstructed forward LUT 148.

The reconstruction section 109 generates a reconstructed HDR image 160. The reconstructed HDR image 160 is reconstructed from the reconstructed LDR image 142 and (i) the reconstructed exposure map 146, (ii) the generated backward LUT 158, or (iii) One or possibly more.

Referring to FIG. 2, a flow diagram illustrates a process 200 that illustrates an implementation of an encoding device and a process. The process 200 also illustrates a structure for performing the described operations of the process 200. Alternatively, the process 200 is performed using the structure of the system 100, in various implementations.

The process 200 includes decomposing the HDR image into LDR and reconstruction information (210). Operation 210 is performed by decomposing HDR image 110 into LDR image 112 and reconstruction information 114, in various implementations. The reconstruction information allows reconstruction of the HDR image.

The process 200 also includes encoding 220 LDR images and encoding 230 reconstruction information. Operation 220, in various implementations, is performed by the encode section 104 in generating the encoded LDR image 122. Similarly, operation 230 is performed by encode section 104 in generating encoded exposure map 126 or encoded LUT 128, in various implementations.

Referring to FIG. 3, a flow diagram illustrates a process 300 that illustrates an implementation of a decoding apparatus and process. Process 300 also illustrates a structure for performing the described operations of process 300. Alternatively, the process 300 is performed using the structure of the system 100, in various implementations.

Process 300 includes decoding the encoded LDR image (310). Operation 310 is performed in various implementations by generating a reconstructed LDR image 142.

The process 300 also includes decoding the encoded reconstruction information (320). The reconstruction information allows reconstruction of the HDR image from the LDR image and the reconstruction information. Operation 320 may be performed in one or more of the following ways: (i) reconstructed exposure map 146, (ii) reconstructed forward LUT 148, or (iii) reconstructed backward LUT 149, And decode section 107 which decodes reconstruction information signal section 134 to generate more than that.

Process 300 also includes reconstructing the HDR image based on the decoded LDR image and the decoded reconstruction information (330). The operation 330 may include, in various implementations, reconstructed LDR image 142 and (i) reconstructed exposure map 146, (ii) generated backward LUT 158, or (iii) reconstructed backward LUT 149, < / RTI > and possibly more. In various implementations, operation 330 also includes generating the generated backward LUT 158.

Several specific implementations of the process 200 will now be described in more detail. Several implementations decompose an HDR signal (possibly including multiple images) into multiple layers or components. There are a number of ways to decompose an HDR signal into, for example, two layers. Several implementations for decomposing the HDR signal into the LDR layer and exposure map to perform one variation of operation 210 are described below.

The first approach applies a tone mapping algorithm to each HDR image to obtain tone mapped video, which is an LDR video signal. After applying the tone mapping algorithm, the exposure map is obtained using the following equation:

In the above equation:

- H (i, j) is a linear HDR luminance value.

The HDR image may be in various color spaces, for example RGB (red-green-blue). In various implementations, we focus on compression of luminance channels and use traditional methods to compress chromatic channels. Also, HDR is a relative term in context. In various implementations, the HDR pixel value is a 10 bit, 12 bit, or floating point representation.

- L (i, j) is an 8-bit gamma corrected pixel value equal to the LDR pixel value corresponding to H (i, j) divided by 255 in certain implementations, lt; / RTI >

Gamma encoding is the name of the nonlinear operation used to code and decode luminance or tristimulus values in video or still image systems (see, for example, http://en.wikipedia.org/wiki/Gamma_correction ). A typical gamma value is 2.2, which is used in many computers.

In the following equation, "x" is a gamma corrected pixel value, which has a range of 0 to 255. "Y" is a linear luminance value. "M" is a scaling constant that defines the maximum luminance of a particular system. For example, in a display system, "M" is the maximum luminance value.

- f () is an inverse response function that can convert a gamma corrected pixel value to a linear amount.

The linear amount is often desired because in many cases the HDR source is in a linear domain. "Linear" means that the luminance value is proportional to the number of photons that hit the camera's sensor. In some terms, it is also referred to as raw pixel data. An example of f () is the equation given above, which is:

- Q () is a quantization function that converts a floating-point number to a fixed-point number. Q () may be uniform or non-uniform. If Q () is non-uniform, then the decoder side needs to know how to perform inverse quantization when the decoder side is normally receiving data. Additional information may be transmitted.

The log function usually has the effect of reducing the range of output, perhaps among other things.

Using this approach to generate the exposure map may produce an uneven smoothed exposure map. Critical exposure maps can be difficult to compress.

An alternative approach is to first create a "fine" exposure map, and then impose a smoothness constraint on the resulting exposure map. Precise exposure maps can be obtained, for example, using bidirectional filters for HDR images as shown in the following references, for example, whose entirety is included herein by reference for all purposes: C. Tomasi, R. Manduchi, Bilateral Filtering for Gray and Color Images, 1998 Proceedings of the Sixth International Conference on Computer Vision, Page 839.

The precision exposure map may also be obtained, for example, using a weighted least squares filter for an HDR image as shown in the following reference, for example, which is hereby incorporated by reference in its entirety for all purposes: Can be: Zeev Farbman et al. Edge-preserving decompositions for multi-scale tone and detail manipulation, ACM SIGGRAPH 2008.

The term "fine" may be unnecessary in certain frameworks. For example, using a weighted least squares filter is a way to obtain an exposure map. In the Zeev paper described above, the normalization method is used to enforce smoothness constraints.

For example, in one implementation, assume that you have a logarithm-compressed HDR image (matrix H) obtained by an applied logarithmic function with base 2 and want to obtain an exposure map (matrix E). We will solve the following optimization problem:

Here, the two-variable function F is a normalization function and may take the form as provided in the paper by Zeev et al. "[lambda]" is a constant controlling the intensity of smoothness.

A smoothness constraint is implied in the optimization problem. This can be explained, for example, in the case of a bidirectional filter. The bi-directional filter applies strong filtering when neighboring pixels are similar, but applies weak filtering when neighboring pixels are quite different. As a result, sharp / strong edges are maintained, but small details are smoothed. The weighted minimum filtering achieves the same general purpose using different mathematical formulations.

Note that the implementation determines the exposure map directly from the HDR image. In contrast, Equation 1 uses an HDR image and an LDR image to determine an exposure map. Basically, once you identify either the LDR map or the exposure map, the others are obtained immediately.

The LDR layer can then be obtained by applying a precise exposure map using Equation 2 below. Finally, the precise exposure map is quantized to a fixed point number and prepared for compression. More specifically, given a precise exposure map E _p (i, j), the red channel r of the LDR layer is:

Lt; / RTI >

here,

- R (i, j) is the linear value of the red component of the HDR image,

- g () is a gamma correction function as described above,

- S () is a saturating function as described below:

Other color channels may be obtained in a similar manner. After generating the LDR layer, the precise exposure map is quantized using the function Q () described above. Thus, all inputs to the next step are fixed-point (usually 8-bits).

After decomposition is performed, the two layers are compressed in multiple implementations. The LDR layer may be compressed using a conventional video compressor, such as, for example, an H.264 video compressor. This performs, for example, operation 220. The exposure map is also compressed and thus performs, for example, operation 230. However, several techniques can be used. The exposure map is, in many implementations, a piecewise smoothed signal with low entropy. The inventors have also observed, in many implementations, that the exposure map has a strong correlation with the LDR layer. For example, the edges are often placed in the same place in both the LDR layer and the exposure map. Accordingly, several techniques previously applied to compress depth maps can be applied to compress exposure maps.

One such technique is to use joint bidirectional filters as described in PCT Publication No. WO 2011/046607 (PCT / US10 / 002744), published April 21, 2011, which is hereby incorporated by reference in its entirety for all purposes . Joint bidirectional filtering can be applied, for example, by replacing the video image of PCT Publication WO 2011/046607 with the LDR image of the present application and replacing the depth map of PCT Publication WO 2011/046607 with the exposure map of the present application. This substitution is expected to produce good results at least because the edges of the exposure map and the LDR image are usually co-located, such as the depth map in PCT Publication WO 2011/046607 and the edges of the video image. Several such implementations replace the deblocking filter of PCT Publication WO 2011/046607 with an in-loop filter to obtain a better recovered exposure map to use as a predictive reference.

Other such techniques involve geometric partitioning as described and applied in PCT Publication WO 2009/051668 (PCT / US08 / 011661), published April 23, 2009, the entirety of which is hereby incorporated by reference for all purposes .

Another such technique includes sparse dyadic mode, as described in PCT Publication WO 2011/046607, which is already incorporated by reference in its entirety for all purposes, and other techniques. Geometrical partitioning as well as sparse diadic mode can be applied by finding a line for a given block and determining a value for each part of the block on either side of the line. The line may be determined, for example, from an LDR image or from an exposure map. In one particular implementation, the line for a given block in the exposure map is determined from the recovered LDR image. Accordingly, the line itself does not need to be transmitted because the decoder can perform the determination itself. In another implementation, the line for a given block of exposure maps is determined from a full exposure map. Thus, the line is transmitted in that implementation because the decoder can not determine the line.

After encoding, the encoded layers may be transmitted or stored, for example. In various implementations, the decoder accesses and decodes the two layers, the LDR image and the exposure map, for a given image. Thus, for example, the decoder performs operations 310 and 320. The decoder then reconstructs the HDR image (e.g., performs operation 330) from the reconstructed LDR image, the reconstructed exposure map.

및

을 획득하기 위해 LDR 이미지 및 노출 맵을 디코딩한다. 여기서, 우리는 단지 휘도 채널만을 고려하고 있다. 유사한 방정식들이 3 개의 칼라 채널들에 대해 획득될 수 있다.In at least one implementation, the reconstruction occurs as follows. The decoder side, respectively,

And

Lt; RTI ID = 0.0 > LDR < / RTI > Here, we are considering only the luminance channel. Similar equations can be obtained for the three color channels.

The restored HDR image is then:

Lt; / RTI >

This is a reverse process and is very similar to the decomposition equation described previously.

Several additional specific implementations of the process 200 will now be described in greater detail. Several implementations decompose an HDR signal (possibly including multiple images) into multiple layers or components. There are a number of ways to decompose an HDR signal into, for example, two layers. Several implementations are described below that decompose the HDR signal into LDR layer and decompression information indicating how the HDR signal can be recovered from the LDR layer, and perform one variation of operation 210.

Note that the exposure map of previous implementations is also considered as reconstruction information indicating how the HDR signal can be reconstructed from the LDR layer.

In various implementations, an HDR image is transformed into an LDR image using tone mapping, which generally refers to quantization. For example, various techniques such as equations, truncation, or lookup tables can be used. For convenience of presentation, we discuss several implementations in the context of lookup tables. However, other mechanisms are equally applicable and considered.

A lookup table ("LUT") may be generated for all HDR images and is sometimes referred to as global tone mapping. Alternatively, the LUT can be created and used for multiple images, such as, for example, a sequence or a movie. Also, a LUT can be created and used for smaller than the entire image, which is often referred to as a local tone mapping. Several implementations create and use LUTs for each slice, block, or partition.

The LUT is generated by analyzing histograms for one or more HDR images in various implementations. Based on the histogram of the HDR values, bins are generated. The bins are often not the same size, and each bean of HDR values is assigned a single LDR value. If the bins are of unequal size, the bins provide a non-uniform mapping between the HDR data values of the HDR image and the LDR data values of the LDR image. Beans are often referred to as quantization beans.

The LUT is constructed using different values in different implementations. For example, the LUT uses the first or last HDR value of each bin in various implementations. The decomposer can then compare the input HDR values to the LUT values to determine the appropriate bin and LDR values.

Several implementations then encode the LDR image and the LUT for storage or transmission. LUTs are not beneficial data. The LUT contains only 256 entries, for example for an implementation that uses 8 bits for LDR data. This is because each of the 256 possible LDR data values corresponds to one entry in the LUT. Thus, for a global tone mapping implementation that uses separate LUTs for all sequences, there are only 256 entries (one LUT) for every sequence of images.

Several implementations form a bitstream from encoded LDR images and encoded LUTs. The LDR images are encoded using, for example, H.264, and the LUTs are encoded using, for example, a lossless coding scheme. Other implementations, of course, use lossy schemes for LUTs. LUTs may be included in an H.264 bitstream, for example, using supplemental enhancement information ("SEI") messages, or using some form of metadata, or transmitted outside the stream.

By providing a LUT to the decoder, an implementation can restore the HDR image. This operation is performed in various implementations using, for example, a decoder, a reconstructor, or a post-processor.

Restoration of the HDR image involves performing an inverse of the tone mapping operation that was performed at the encoding end. In typical implementations, each input LDR value will correspond to a particular LUT HDR value. The LUT HDR values are set at the beginning of a bean, or at the end of a bean in various implementations. The inverse tone mapping can be performed, for example, using its corresponding LUT HDR value, using the HDR value corresponding to the other end of the bean, or using the HDR value corresponding to the center of the bean. A simple mathematical averaging of two adjacent LUT HDR values can be performed. However, in one implementation that uses the central HDR value of each bin, the inverse tone mapping LUT is generated in the decoder using the median values as the LUT entries, as described and illustrated by the generated backward LUT 158 do.

Conventional receivers also apply a dithering algorithm, or other techniques, to improve the appearance of the reconstructed HDR image. Dithering, or other processing may reduce the quantization noise in the reconstructed HDR image.

Referring to FIG. 4, an encoder 1100 illustrates an implementation of an encoder used in various implementations to encode images, such as, for example, LDR images, HDR images, or exposure maps. Encoder 1100 is also used in certain implementations to encode data such as, for example, metadata that provides information about the encoded bitstream. The metadata includes reconstruction information such as, for example, a LUT. Encoder 1100 is implemented in one implementation, e.g., as part of a video transmission system as described below with respect to FIG. It should also be apparent that the blocks of FIG. 4 provide a block diagram of the encoder as well as provide a flowchart of the encoding process.

The input image sequence arrives at the adder 1101 as well as the displacement compensation block 1120, and the displacement estimation block 1118. Note that the displacement refers to, for example, a motion displacement or a disparity displacement. The input image sequence is an LDR layer in one implementation. The other input to the adder 1101 is one of a variety of possible reference picture information items received via the switch 1123.

For example, in the first scenario, mode determination module 1124 in signal communication with switch 1123 is an intra prediction that refers to a block from the same picture (e.g., an LDR picture) in which the encoding mode is currently being encoded . In this first scenario, the adder 1101 receives its input from the intra prediction module 1122. Alternatively, in the second scenario, the mode determination module 1124 may determine that the encoding mode is a displacement that refers to an image (e.g., a different time, or a view, or both) Compensation and estimation. In this second scenario, the adder 1101 receives its input from the displacement compensation module 1120.

In various implementations, intra prediction module 1122 provides a predetermined predictor based on one or more blocks that are neighboring blocks to the block being encoded. In various implementations, intra prediction module 1122 provides a predictor (reference) by retrieving the best reference block in the picture to be encoded.

More specifically, several such predictor-based implementations search within the restoration of these portions of the already encoded current image. In some implementations, the search is limited to blocks that lie at existing block boundaries. However, in other implementations, the search is allowed to search for blocks regardless of whether these blocks cross existing block sectors. Due to the search, such implementations are often more time-intensive and processor-intensive than using only predetermined neighboring blocks as references. However, such implementations usually provide the advantage of finding better predictions of a given block.

Such implementations may result in the best-estimate intra prediction block. Also, in various implementations, the boundaries of the reference block may be located at the sub-pixel boundaries, and the restoration of references involves an interpolation step that restores the actual block to be used as a reference during decoding. Depending on the contents of the pictures, such sub-pixel interpolation implementations may improve compression efficiency as compared to the use of neighboring blocks as references.

The adder 1101 provides a signal to the transform module 1102, which is configured to transform the input signal and provide the transformed signal to the quantization module 1104. The quantization module 1104 is configured to perform quantization on its received signal and output the quantized information to an entropy encoder 1105. [ Entropy encoder 1105 is configured to perform entropy encoding on its input signal to produce a bitstream. The inverse quantization module 1106 is configured to receive quantized signals from the quantization module 1104 and perform inverse quantization on the quantized signals. In turn, inverse transform module 1108 is configured to receive the dequantized signal from inverse quantization module 1106 and perform an inverse transform on its received signal. The output of the inverse transform module 1108 is the recovery of the signal output from the adder 1101.

An adder (more generally referred to as a combiner) 1109 adds the received signals from the inverse transform module 1108 and the switch 1123 and outputs the combined signals to the intra prediction module 1122 and the in- And outputs a resultant signal. Intraprediction module 1122 uses the resulting signal, for example, in coding additional blocks from the current picture. The in-loop filter 1110 filters the recovered image data for a given image and provides it to a depth reference buffer 1112 as described further below. The resulting signal is the recovery of the image sequence signal that is input to the encoder 1100.

Intra prediction module 1122 performs intra prediction as described above using its received signals. The in-loop filter 1110 filters the signals received from the adder 1109 and provides filtered signals to the reference buffer 1112. Reference buffer 1112 provides image information to displacement estimation and compensation modules 1118 and 1120. In one implementation, the reference buffer 1112 stores reference pictures from, for example, other time instances or other views rather than from the current picture. The in-loop filter 1110 is a deblocking filter in one implementation.

In one implementation, in-loop filter 1110 uses neighboring pixels to obtain filtered results for a given pixel in the current block. In various filter designs, neighboring pixels for the current block include pixels from the non-decoding block. Thus, for these filter designs, the current block can not be filtered while it is being decoded. Also, certain previously decoded neighboring pixels can not be filtered until the current block is decoded. As a result, at least one implementation does not use the filtered results in intra prediction. However, the implementation uses the filtered results for the intere side because all blocks from the previous picture (reference picture) are decoded and can be filtered.

The metadata may be added to the encoder 1100 as encoded metadata and combined with the output bitstream from the entropy coder 1105. [ Alternatively, for example, unencoded metadata may be input to the entropy coder 1105 for entropy encoding along with the quantized image sequences.

The data is also provided by the mode determination module 1124 as an output bit stream. The mode determination module 1124 provides the bitstream with information indicating a mode used to encode a given block. Such information often includes an indication of the location of the reference block. For example, in various implementations that use intraprediction and perform a search for a current picture to find a reference block, the mode determination module 1124 uses the disparity vector to indicate the location of the reference. The disparity vector information may be provided to the mode determination module 1124 by the intra prediction module 1122. [

As described further below, the disparity vector information may be separately coded using the disparity vector of the neighboring macroblock as a reference. Also, the disparity vectors of an image may be grouped and additionally encoded to remove entropy since they are likely to have spatial similarity in disparity vectors.

5, a decoder 1200 illustrates an implementation of a decoder that may be used to decode images, for example, LDR images. The decoded images, in one implementation, are provided to a reconstruction or reconstruction device that generates HDR images based on the LDR images. Decoder 1200 is used in other implementations, for example, to decode metadata and / or to decode video data. The metadata provides, for example, information about the LUT, the exposure map, the encoded video images, or the decoded bitstream. In one implementation, decoder 1200 is implemented, for example, as part of a video receiving system as described below with respect to FIG. It should also be apparent that the blocks of FIG. 5 provide a flowchart of the decoding process in addition to providing a block diagram of the decoder.

The decoder 1200 is configured to receive the bitstream using the bitstream receiver 1202. The bitstream receiver 1202 is in signal communication with a bitstream parser 1204 and provides a bitstream to the bitstream parser 1204.

The bitstream parser 1204 sends the residual bitstream to the entropy decoder 1206 and sends the control syntax elements to the mode selection module 1216 and the displacement (motion / disparity) vector Information is transmitted.

The displacement vector information may be, for example, motion vector information or disparity vector information. The motion vector information is typically used in inter prediction to indicate relative motion from the previous image. The disparity vector information is typically used in (i) intra prediction to represent disparity for an individual image, or (ii) intra prediction to represent disparity for a portion of the same image. As is known in the art, disparities typically represent relative offsets, or displacements, between two images. The disparity may also be used to indicate a relative offset or displacement between two portions of the image.

The inverse quantization module 1208 performs inverse quantization on the entropy-decoded signal received from the entropy decoder 1206. Inverse transform module 1210 is also configured to perform an inverse transform on the dequantized signal received from inverse quantization module 1208 and to output an inverse transformed signal to adder 1212 (also referred to as a combiner).

The adder 1212 may receive one of a variety of different signals depending on the decoding mode used. For example, in one implementation, mode determination module 1216 determines whether displacement compensation or intra prediction encoding is performed by the encoder for the block on which it is currently being processed by parsing and analyzing control syntax elements. Depending on the determined mode, the mode selection control module 1216 may access and control the switch 1217 based on the control syntax elements so that the adder 1212 may receive from the displacement compensation module 1226, or from the intra prediction module 1218 Signals.

Here, intra prediction module 1218 is configured to perform intra prediction to decode the block using references to the same picture being currently decoded. In turn, the displacement compensation module 1226 decodes the block using references to blocks of other previously processed pictures that are different (e.g., from different times or views, or both) from the pictures currently being decoded So as to perform the displacement compensation.

After receiving the prediction or compensation information signals, the adder 1212 adds the prediction or compensation information signals to the inverse transformed signal for transmission to the in-loop filter 1214. [ The in-loop filter 1214 is, for example, a deblocking filter that filters the blocking artifacts. The adder 1212 also outputs the added signal to the intra prediction module 1218 for use in intra prediction.

The in-loop filter 1214 is configured to filter its input signal and output decoded pictures. In addition, in-loop filter 1214 provides the filtered signal to reference buffer 1220. The reference buffer 1220 is configured to parse its received signal to allow and assist in displacement compensation decoding by the displacement compensation module 1226, which provides the parsed signals to the reference buffer 1220. Such parsed signals may be, for example, all or part of several pictures that may have been used as references.

The metadata may be included in the bitstream provided to the bitstream receiver 1202. The metadata may be parsed by the bitstream parser 1204 and decoded by the entropy decoder 1206. The decoded metadata may be extracted from the decoder 1200 after entropy decoding using an output (not shown).

In at least one implementation, many of the blocks of FIG. 5 perform inverse operations of corresponding blocks of FIG. For example, in one implementation:

The entropy decoder 1206 performs an inverse of the entropy encoder 1105,

- Inverse quantization module 1208 performs an inverse of quantization module 1104,

Inverse transform module 1210 performs an inverse of transform module 1102.

Moreover, as already described above, in at least one implementation, many of the blocks of FIG. 5 perform the same operations as the corresponding blocks of FIG. For example, in the implementation of honey:

- in-loop filter 1214 performs the same operations as in-loop filter 1110,

The intra prediction module 1218 performs the same operations as the intra prediction module 1122,

The displacement compensation module 1226 performs the same operations as the displacement compensation module 1120.

Referring now to FIG. 6, there is shown a video transmission system or apparatus 1600 to which the above-described features and principles may be applied. The video transmission system or apparatus 1600 may be a head-end or base station that transmits signals using any of a variety of media, for example, satellite, cable, telephone line, or terrestrial broadcast, Lt; / RTI > The video transmission system or device 1600 may also or alternatively be used to provide a signal for storage, for example. Transmissions may be provided over the Internet or some other network. The video transmission system or device 1600 may generate and communicate, for example, video content and other content such as, for example, metadata. It should also be clear that the convexes in Figure 6 provide a flow diagram of the video transmission process in addition to providing a block diagram of the video transmission system or apparatus.

A video transmission system or device 1600 receives input video from a processor 1601. In one implementation, the processor 1601 simply provides video images, such as LDR images, to a video transmission system or device 1600. However, in other implementations, the processor 1601 alternatively or additionally provides exposure maps and / or LUTs to the video transmission system or device 1600. [ The processor 1601 may also provide metadata to a video transmission system or device 1600, where the metadata may be associated with, for example, one or more input images and may include, for example, a LUT.

The video transmission system or apparatus 1600 includes an encoder 1602 and a transmitter 1604 capable of transmitting an encoded signal. Encoder 1602 receives video information from processor 1601. The video information may include, for example, video images, and / or exposure maps. Encoder 1602 generates the encoded signal (s) based on video and / or other information. Encoder 1602 is the encoder 1100 of FIG. 4 in one implementation. In various implementations, the encoder 1602 is, for example, an AVC encoder.

The encoder 1602 may include submodules that include an assembly unit that, for example, receives information from multiple pieces and assembles them into a structured format for storage or transmission. The information of the multiple pieces may include, for example, encoded or unencoded video, exposure map values, LUTs, other metadata or information, and various elements such as motion vectors, coding mode indicators, and syntax elements . In some implementations, the encoder 1602 includes a processor 1601, and thus performs operations of the processor 1601.

Transmitter 1604 receives the encoded signal (s) from encoder 1602 and transmits the encoded signal (s) in one or more output signals. Transmitter 1604 may be configured to transmit a program signal having one or more bit streams representing, for example, encoded pictures and / or information associated therewith. Typical transmitters include, for example, providing error-compensated coding, interleaving data in a signal, randomizing energy in a signal, and modulating a signal onto one or more carriers using a modulator 1606 And performs one or more of the following functions. The transmitter 1604 may include an antenna (not shown) or may interface with an antenna. In addition, implementations of the transmitter 1604 may be limited to the modulator 1606.

The video transmission system or device 1600 is also communicatively coupled to a storage unit 1608. In one implementation, storage unit 1608 is coupled to encoder 1602, storage unit 1608 stores the encoded bit stream from encoder 1602, and optionally transmitter 1604 stores its stored bits Stream. In another implementation, storage unit 1608 is coupled to transmitter 1604 and stores a bit stream from transmitter 1604. The bitstream from the transmitter 1604 may include one or more encoded bitstreams that are further processed, for example, by the transmitter 1604. Storage unit 1608 is one or more of a standard DVD, Blu-ray disc, hard drive, or some other storage device in different implementations.

In various implementations, a video transmission system or apparatus 1600 performs a process 200. For example, the processor 1601 performs an operation 210 and the encoder 1602 performs operations 220 and 230. [

Referring to FIG. 7, there is shown a video receiving system or apparatus 1700 to which the above-described features and principles may be applied. The video receiving system or device 1700 may be configured to receive signals via various media such as, for example, satellite, cable, telephone line, or terrestrial broadcast. The signals may be received over the Internet or some other network. It should also be clear that the convexes in Figure 7 provide a flow diagram of the video receiving process in addition to providing a block diagram of the video receiving system or apparatus.

The video receiving system or device 1700 may be configured to receive, for example, a cell phone, a computer, a set top box, a television, or an encoded video and for processing, e.g., Or other device that provides a decoded video signal for storage. Thus, the video receiving system or device 1700 may provide its output to, for example, a screen of a television, a computer monitor, a computer (for storage, processing or display), or some other storage, processing or display device .

A video receiving system or device 1700 can receive and process video information. The video information may include, for example, video images, LUTs, and / or exposure maps. The video receiving system or device 1700 includes a receiver 1702 that receives an encoded signal, such as, for example, the signals described in the embodiments of the present application. Receiver 1702 may include, for example, a signal that provides one or more LDR images, HDR images, LUTs, and / or exposure maps, or a signal from a video transmission system 1600 (e.g., (E.g., from transmitter 1608 or transmitter 1604).

Receiver 1702 may be configured to receive a program signal having a plurality of bit streams representing, for example, encoded pictures (e.g., video pictures and / or depth pictures). Typical receivers include, for example, receiving a modulated and encoded data signal, demodulating a data signal from one or more carriers using demodulator 1704, de-randomizing the energy in the signal, randomizing the data in the signal, deinterleaving the data in the signal, and error correction decoding the signal. The receiver 1702 may include an antenna (not shown) or may interface with an antenna. Implementations of receiver 1702 may be limited to demodulator 1704.

The video receiving system or apparatus 1700 includes a decoder 1706. Decoder 1706 is decoder 1200 of FIG. 5 in one implementation.

Receiver 1702 provides the received signal to decoder 1706. [ The signal provided by decoder 1702 to decoder 1706 may include one or more encoded bitstreams. Decoder 1706 outputs a decoded signal, such as, for example, decoded video signals including video information, exposure maps, LUTs, or other metadata or reconstruction information. Decoder 1706 may be, for example, an AVC decoder.

The video receiving system or device 1700 is also communicatively coupled to a storage unit 1707. In one implementation, storage unit 1707 is coupled to receiver 1702, and receiver 1702 accesses the bit stream from storage unit 1707 and / or stores the received bit stream . In another implementation, storage unit 1707 is coupled to decoder 1706, and decoder 1706 accesses the bit stream from storage unit 1707 and / or stores the decoded bit stream in storage unit 1707 . The bit stream accessed from storage unit 1707, in different implementations, includes one or more encoded bit streams. Storage unit 1707, in different implementations, is one or more of a standard DVD, Blu-ray disc, hard drive, or some other storage device.

The output video from decoder 1706 is provided to processor 1708, in one implementation. Processor 1708 is, in one implementation, a processor configured to perform reconstruction or reconstruction of HDR images. In some implementations, the decoder 1706 includes a processor 1708 and thus performs operations of the processor 1708. In other implementations, processor 1708 is part of a downstream device, such as, for example, a set top box or a television.

In various implementations, a video receiving system or device 1700 performs process 300. [ For example, decoder 1706 performs operations 310 and 320, and processor 1708 performs operation 330. [

The present application provides a number of block diagrams and / or flowcharts, including the diagrams of Figures 1-7. It should be apparent that the block diagrams and / or flowcharts of the present application provide both a flowchart describing the process and a block describing the functional blocks of the device.

For example, as previously described, the flow diagram of FIG. 1 describes a flow process that includes the operations listed in FIG. However, Figure 1 also provides a block diagram that implements the flow. In one implementation, for example, (i) a block for an HDR image 110 represents an image receiving device, (ii) a block for an LDR image 112 represents a decomposition component that generates an LDR image, and (iv) the block for the LDR image portion 132 represents the bitstream generator; and (v) the block for the reconstructed LDR image 142 represents Decoder. In this implementation, the other blocks of FIG. 1 are interpreted in a similar manner to provide a complete block diagram that implements the flow.

For example, as previously described, the flow chart of FIG. 2 describes a flow process that includes the operations listed in FIG. However, Figure 2 also provides a block diagram that implements that flow. In one implementation, for example, each of the blocks for each of operations 210-230 represents a component that performs each operation. That is, for example, the block for operation 210 represents a component that performs operations to decompose the HDR image into LDR image and reconstruction information. In another implementation, FIG. 3 is interpreted in a manner similar to that described with respect to FIG.

For example, as previously described, the block diagram of FIG. 4 describes a system or apparatus that includes the components shown in FIG. Figure 4, however, also provides a flow chart for performing the functions of the blocks. In one implementation, for example, a block for transform module 1102 that is (i) a component represents an operation for performing a transform, (ii) a block for in-loop filter 1110 - indicates an operation to perform loop filtering. In this implementation, the other blocks of FIG. 4 are interpreted in a similar manner to provide a complete flow diagram of performing the functions of the blocks. In other implementations, Figures 5-7 are interpreted in a manner similar to that described for Figure 4.

We thus provide one or more implementations with particular features and aspects. In particular, we provide several implementations related to decomposition and reconstruction (or restoration) of HDR images. However, variations of these implementations and additional applications are contemplated and within the present disclosure, features and aspects of the described implementations may be configured for other implementations.

Several implementations and features described in this application may be used in the context of an AVC with an AVC standard, and / or an AVC with an MVC extension (Annex H), and / or an SVC extension (Annex G). Additionally, these implementations and features may be used in other standards (existing or future) contexts, or in contexts not accompanied by standards.

Reference to "an embodiment" or "an embodiment" or "an implementation" or "an implementation" of these principles, as well as other variations, Quot; is included in at least one embodiment of the present principles. Thus, the appearances of the phrase "in an embodiment" or "in an embodiment " or" in one embodiment "or" in an implementation ", as well as any other & It does not refer to a form.

The present application or claims may also refer to "determining " information of multiple pieces. Determining the information may include, for example, one or more of estimating the information, calculating the information, predicting the information, or retrieving information from the memory.

In addition, the present application or claims may refer to "accessing " information of multiple pieces. Accessing information may include receiving information, retrieving information (e.g., memory), storing information, processing information, transmitting information, moving information, It may include one or more of copying, deleting information, calculating information, determining information, predicting information, or estimating information.

Various implementations refer to "images" and / or "images ". The terms "image" and "image" are used interchangeably throughout this document and are intended to be broad terms. The "image" or "image" may be, for example, all or part of a frame or field. The term "video" refers to a sequence of images (or images). The image, or image, may include, for example, any of several video components or combinations thereof. Such components, or combinations thereof, may include, for example, luminance, chrominance, Y (of YUV or YCbCr or YPbPr), Y (of YUV), V of (of YUV), Cb of YCbCr, , Pb (of YPbPr), Pr (of YPbPr), Red (of RGB), Green of (RGB), Blue of (RGB), S-Video, and any of these components or positives . The "image" and "image" may also or alternatively include, for example, conventional 2D video, exposure map, disparity map for 2D video images, depth map corresponding to 2D video images, Quot; refers to a variety of different types of content.

The "exposure map", "depth map", "disparity map", "edge map", and similar terms are also intended to be broad terms. A map generally refers to a set of data, including, for example, a particular type of information. However, a map may contain other types of information not represented by its name. For example, the depth map typically includes depth information, but may also include other information such as, for example, video or edge information. Also, for example, maps such as exposure maps or depth maps do not have to be visually useful or meaningful, as do video images. However, maps can provide and often provide visually useful or meaningful information. For example, depth maps typically provide images where objects and depth can be ascertained by the human eye.

The term "layer" is used in this document to refer to, for example, the HDR layer, the LDR layer, and the exposure map layer. A layer may include a variety of different elements. Typically, the HDR layer includes, for example, an HDR image. More generally, the HDR layer is a hierarchy or level in an organized or hierarchical sense, including, for example, HDR elements such as HDR images.

A "signal" refers to, for example, a bit stream. Accordingly, the HDR signal typically includes a bit stream representing an HDR element, such as, for example, an HDR image from the HDR layer.

The terms "neighbor" and "neighboring" are used throughout this application. By way of example, the first block or pixel is referred to as the first block or neighbor to the second block or pixel if the pixel contacts the second block or pixel. Thus, a given block or pixel typically has eight neighbors, including blocks or pixels at the left, right, top, bottom, and four corners.

Quot ;, "and / or ", and" at least one of ", for example, in the cases of "A / B", "A and / Is intended to include selection of only the first listed option (A), or only the second listed option (B), or both options (A and B). As another example, in the cases of "A, B, and / or C" and "At least one of A, B, and C" and "At least one of A, B, or C" (A) alone, or only the second listed option (B), or only the third listed option (C), or only the first and second listed options (A and B), or The selection of only the first and third listed options A and C or only the second and third listed options B and C or the selection of all three options A and B and C, / RTI > This may be extended for the listed items, as is readily apparent by those skilled in the art in these and related techniques.

Also, many implementations may be implemented using an encoder (e.g., encoder 1100 or 1602), a decoder (e.g., decoder 1200 or 1706), a post-processor 1708), or a pre-processor (e.g., processor 1601) that provides input to an encoder. In addition, other implementations are contemplated by this disclosure.

The implementations described herein may be implemented in, for example, a method or process, an apparatus, a software program, a data stream, or a signal. Although discussed only in the context of a single form of implementation (for example, discussed only as a method), an implementation of the features discussed may also be implemented in other forms (e.g., a device or a program). The device may be implemented in, for example, suitable hardware, software, and firmware. The methods may be implemented in devices such as, for example, a processor, generally referred to as processing devices, including, for example, a computer, microprocessor, integrated circuit, or programmable logic device. The processors also include communication devices such as, for example, computers, cell phones, portable / personal digital assistants ("PDAs"), and other devices that facilitate communication of information between end-users.

The implementations of the various processes and features described herein may be implemented in a variety of different devices or applications, including, for example, data encoding, data decoding, HDR processing, view generation, depth or disparity processing, / RTI > and / or other processing of disparity maps. Examples of such equipment include, but are not limited to, an encoder, a decoder, a post-processor that processes the output from the decoder, a preprocessor that provides input to the encoder, a video coder, a video decoder, a video codec, HDR display devices, laptops, personal computers, cell phones, PDAs, and other communication devices. As will be apparent, the equipment is mobile and may even be installed in a vehicle.

Also, the methods may be implemented by instructions executed by a processor, and such instructions (and / or data values generated by the implementation) may be stored, for example, in an integrated circuit, a software carrier or a hard disk, Such as optical disks, random access memories ("RAMs "), or read only memories (" ROMs ") such as diskettes ("CDs"), optical discs (e.g., DVDs or digital video discs sometimes referred to as digital versatile discs) Or may be stored in a processor readable medium, such as another storage device. The instructions may form an application program typed into the processor readable medium. The instructions may be, for example, in hardware, firmware, software, or a combination. The instructions may be found, for example, in an operating system, in an individual application, or a combination of both. Thus, a processor may be characterized, for example, as both a device configured to perform a processor and a device including a processor-readable medium (such as a storage device) having instructions for performing the process. The processor readable medium may also store data values generated by an implementation in addition to or instead of the instructions.

As will be apparent to those of ordinary skill in the art, implementations may generate various signals, for example formatted to carry information that may be stored or transmitted. The information may include, for example, instructions that perform the method, or data generated by one of the described implementations. For example, the signal may be formatted to carry the rules for writing or reading the syntax as data, or the actual syntax-values generated using syntax rules as data. Such a signal may be formatted, for example, as an electromagnetic wave (using, for example, a radio frequency portion of the spectrum) or as a baseband signal. The formatting may include, for example, encoding the data stream and modulating the carrier into the encoded data stream. The information carried by the signal may be, for example, analog or digital information. The signal may be transmitted over a variety of different wired or wireless links as is known. The signal may be stored on the processor readable medium.

A number of implementations have been described. Nevertheless, it should be understood that various modifications may be made. For example, elements of different implementations may be combined, supplemented, altered, or eliminated to produce different implementations. It is also to be understood that other structures and processes may be used instead of those disclosed and that implementations of the results may be implemented in at least substantially the same manner (s) to achieve at least substantially the same result (S) < / RTI > Accordingly, these and other implementations are contemplated by the present application.

Claims (37)

Generating an exposure map that allows, from a higher dynamic range image, a lower dynamic range image and the higher dynamic range image to be restored from the lower dynamic range image, Wherein the entry is a two-dimensional matrix that represents a multiplier for each pixel used to recover the higher dynamic range image from the lower dynamic range image; generating the lower dynamic range image and the exposure map ;
Imposing a smoothness constraint on the exposure map to generate a smoothed exposure map;
Encoding the lower dynamic range image;
Encoding the smoothed exposure map; And
And transmitting the lower dynamic range image and the smoothed exposure map. The method according to claim 1,
Wherein the encoding of one or more of the lower dynamic range image and the exposure map utilizes a correlation between the lower dynamic range image and the exposure map. 3. The method of claim 2,
Wherein the correlation comprises an edge collocated in both the lower dynamic range image and the exposure map. The method according to claim 1,
Wherein the exposure map is encoded based on restoration of the lower dynamic range image. The method according to claim 1,
Wherein the exposure map is encoded using at least one of (i) joint bidirectional filtering, (ii) geometric partitioning, or (iii) sparse dyadic mode. The method according to claim 1,
Wherein generating the lower dynamic range image and the exposure map further comprises:
Generating the exposure map using the higher dynamic range image; And
And using the exposure map to generate the lower dynamic range image. The method according to claim 1,
Wherein generating the lower dynamic range image and the exposure map further comprises:
Generating the lower dynamic range image using the higher dynamic range image; And
And generating the exposure map using the lower dynamic range image. The method according to claim 1,
Wherein the step of generating the lower dynamic range image further comprises using the non-uniform mapping between the data values of the higher dynamic range image and the data values of the lower dynamic range image to convert the higher dynamic range image into the lower dynamic range Into an image,
Wherein the exposure map describes one or more of (i) the non-uniform mapping or (ii) an inverse transformation that allows restoration of the higher dynamic range image. 9. The method of claim 8,
Wherein the exposure map comprises a look-up table representing higher dynamic range data values and ranges of associated lower dynamic range data values. 9. The method of claim 8,
Wherein the exposure map comprises a look-up table representing the restored higher dynamic range data values associated with a particular lower dynamic range data value. The method according to claim 1,
≪ / RTI > further comprising constructing a bitstream comprising the lower dynamic range image encoded and the exposed exposure map encoded. 12. The method of claim 11,
Wherein constructing the bitstream comprises including the encoded exposure map as metadata. 12. The method of claim 11,
Wherein constructing the bitstream comprises including the encoded exposure map as a supplemental enhancement information message. The method according to claim 1,
Wherein encoding the lower dynamic range image comprises encoding the lower dynamic range image using H.264. The method according to claim 1,
Wherein generating the lower dynamic range image and the exposure map comprises decomposing the higher dynamic range image,
Wherein the exposure map allows the higher dynamic range image to be reconstructed from the lower dynamic range image. Generating an exposure map that permits the restoration of the higher dynamic range image from the higher dynamic range image and the lower dynamic range image, wherein the exposure map further comprises: A two-dimensional matrix representing a multiplier for each pixel used to recover the higher dynamic range image from the lower dynamic range image,
And applying a smoothness constraint to the exposure map to generate a smoothed exposure map;
An encoder configured to encode the lower dynamic range image and encode the smoothed exposure map; And
And a transmitter for the lower dynamic range image and the smoothed exposure map. Means for generating an exposure map that allows for restoration of the higher dynamic range image from the higher dynamic range image and the lower dynamic range image, Wherein the entry is a two-dimensional matrix that represents a multiplier for each pixel used to recover the higher dynamic range image from the lower dynamic range image, the means for generating the lower dynamic range image and the exposure map ;
Means for imposing a smoothness constraint on the exposure map to generate a smoothed exposure map;
Means for encoding the lower dynamic range image;
Means for encoding the smoothed exposure map; And
And a transmitter for the lower dynamic range image and the smoothed exposure map. 17. A non-transitory processor readable medium having stored thereon instructions,
The instructions cause one or more processors to:
Creating an exposure map that permits the restoration of the higher dynamic range image from the higher dynamic range image and the lower dynamic range image, Range image representing a multiplier for each pixel used to recover the higher dynamic range image from the lower dynamic range image; and generating the lower dynamic range image and the exposure map;
Imposing a smoothness constraint on the exposure map to generate a smoothed exposure map;
Encoding the lower dynamic range image;
Encoding the smoothed exposure map; And
Transmitting the lower dynamic range image and the smoothed exposure map
In a non-volatile manner. delete delete delete delete delete delete 18. A non-transitory processor readable medium having stored thereon a signal structure,
Wherein the signal structure comprises:
A lower dynamic range section including an encoded lower dynamic range image; And
An exposure map section comprising an encoded exposure map, said exposure map allowing restoration of a higher dynamic range image from said lower dynamic range image, said exposure map comprising: Wherein the exposure map section is a two-dimensional matrix representing a multiplier for each pixel used to recover the higher dynamic range image. Decoding an encoded lower dynamic range image;
Decoding the encoded exposure map, wherein the decoded exposure map allows restoration of a higher dynamic range image from the lower dynamic range image, wherein the decoded exposure map indicates that each entry has a lower dynamic range A two-dimensional matrix representing a multiplier for each pixel used to recover the higher dynamic range image from the image, wherein a smoothness constraint is imposed on the decoded exposure map; step; And
And restoring the higher dynamic range image based on the decoded lower dynamic range image and the decoded exposure map. 27. The method of claim 26,
Wherein the encoding of one or more of the lower dynamic range image and the exposure map utilizes a correlation between the lower dynamic range image and the exposure map,
Wherein decoding the exposure map is based on decoding the lower dynamic range image. 27. The method of claim 26,
Wherein the exposure map describes a non-uniform mapping between higher dynamic range data values and lower dynamic range data values used to generate the lower dynamic range image from a higher dynamic range image. 27. The method of claim 26,
Wherein the exposure map describes a non-uniform mapping between higher dynamic range data values and lower dynamic range data values that allows restoration of a higher dynamic range image from the lower dynamic range image. 27. The method of claim 26,
The exposure map includes a non-uniform mapping between lower dynamic range data values and higher dynamic range data values,
The step of reconstructing the higher dynamic range image may include generating the higher dynamic range data values using (i) the non-uniform mapping and (ii) the lower dynamic range data values from the lower dynamic range image How to. 27. The method of claim 26,
The exposure map includes a non-uniform mapping between higher dynamic range data values and lower dynamic range data values,
Wherein the step of reconstructing the higher dynamic range image further comprises: (i) generating an inverse mapping based on the non-uniform mapping, and (ii) interpolating the lower dynamic range data from the inverse mapped and decoded lower dynamic range image Values to generate higher dynamic range data values. 27. The method of claim 26,
Wherein decoding the encoded exposure map comprises decoding one or more of an SEI message or metadata. 27. The method of claim 26,
Wherein the decoding of the encoded lower dynamic range image comprises accessing the encoded lower dynamic range image from the received bitstream,
Wherein decoding the encoded exposure map comprises accessing the encoded exposure map from the received bitstream. 27. The method of claim 26,
Wherein the exposure map allows reconstruction of the higher dynamic range image from the lower dynamic range image,
Wherein reconstructing the higher dynamic range image comprises reconstructing the higher dynamic range image based on the decoded lower dynamic range image and the decoded exposure map. A decoder configured to decode an encoded lower dynamic range image and to decode an encoded exposure map, wherein the decoded exposure map allows restoration of a higher dynamic range image from the lower dynamic range image Wherein the decoded exposure map is a two dimensional matrix that represents a multiplier for each pixel used to recover the higher dynamic range image from the lower dynamic range image, The decoder being imposed on the decoded exposure map; And
And a processor configured to recover the higher dynamic range image based on the decoded lower dynamic range image and the decoded exposure map. Means for decoding an encoded lower dynamic range image;
Wherein the decoded exposure map allows restoration of a higher dynamic range image from the lower dynamic range image, and wherein the decoded exposure map indicates that each entry has a lower dynamic range A two-dimensional matrix representing a multiplier for each pixel used to recover the higher dynamic range image from the image, wherein a smoothness constraint is imposed on the decoded exposure map; Way; And
Means for recovering the higher dynamic range image based on the decoded lower dynamic range image and the decoded exposure map. 17. A non-transitory processor readable medium having stored thereon instructions,
The instructions cause one or more processors to:
Decoding the encoded lower dynamic range image;
Wherein the exposure map permits the restoration of a higher dynamic range image from the lower dynamic range image, the exposure map further comprising: each entry having a higher dynamic range image from the lower dynamic range image, Decoding the encoded exposure map in which a smoothness constraint is imposed on the exposure map, the two-dimensional matrix representing a multiplier for each pixel used to recover a dynamic range image; And
And restoring the higher dynamic range image based on the decoded lower dynamic range image and the decoded exposure map
In a non-volatile manner.

Images